Brendan O'Donoghue

53 papers A* 15A 1Journal 33Unranked 4

Year	Rank	Type	Title / Venue / Authors
2023	A*	`conf`	Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization. ICML Brendan O'Donoghue
2023	J	`jnl`	Efficient exploration via epistemic-risk-seeking policy optimization. CoRR Brendan O'Donoghue
2023	A*	`conf`	Optimistic Meta-Gradients. NeurIPS Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado Philip van Hasselt, András György, Satinder Singh
2023	J	`jnl`	Optimistic Meta-Gradients. CoRR Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado van Hasselt, András György, Satinder Singh
2023	J	`jnl`	POMRL: No-Regret Learning-to-Plan with Increasing Horizons. Trans. Mach. Learn. Res. Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy
2023	A*	`conf`	Probabilistic Inference in Reinforcement Learning Done Right. NeurIPS Jean Tarbouriech, Tor Lattimore, Brendan O'Donoghue
2023	J	`jnl`	Probabilistic Inference in Reinforcement Learning Done Right. CoRR Jean Tarbouriech, Tor Lattimore, Brendan O'Donoghue
2023	A*	`conf`	ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. ICML Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
2023	J	`jnl`	ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. CoRR Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
2022	J	`jnl`	On the connection between Bregman divergence and value in regularized Markov decision processes. CoRR Brendan O'Donoghue
2022	J	`jnl`	POMRL: No-Regret Learning-to-Plan with Increasing Horizons. CoRR Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy
2022	A*	`conf`	The Neural Testbed: Evaluating Joint Predictions. NeurIPS Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Dieterich Lawson, Botao Hao, Brendan O'Donoghue, Benjamin Van Roy
2021	J	`jnl`	Discovering Diverse Nearly Optimal Policies withSuccessor Features. CoRR Tom Zahavy, Brendan O'Donoghue, André Barreto, Volodymyr Mnih, Sebastian Flennerhag, Satinder Singh
2021	A*	`conf`	Discovering a set of policies for the worst case reward. ICLR Tom Zahavy, André Barreto, Daniel J. Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh
2021	J	`jnl`	Discovering a set of policies for the worst case reward. CoRR Tom Zahavy, André Barreto, Daniel J. Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh
2021	J	`jnl`	Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? CoRR Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Botao Hao, Morteza Ibrahimi, Dieterich Lawson, Xiuyuan Lu, Brendan O'Donoghue, Benjamin Van Roy
2021	A	`conf`	Matrix games with bandit feedback. UAI Brendan O'Donoghue, Tor Lattimore, Ian Osband
2021	J	`jnl`	Operator Splitting for a Homogeneous Embedding of the Linear Complementarity Problem. SIAM J. Optim. Brendan O'Donoghue
2021	A*	`conf`	Practical Large-Scale Linear Programming using Primal-Dual Hybrid Gradient. NeurIPS David L. Applegate, Mateo Díaz, Oliver Hinder, Haihao Lu, Miles Lubin, Brendan O'Donoghue, Warren Schudy
2021	A*	`conf`	Reward is enough for convex MDPs. NeurIPS Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
2021	J	`jnl`	Reward is enough for convex MDPs. CoRR Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
2021	A*	`conf`	Sample Efficient Reinforcement Learning with REINFORCE. AAAI Junzi Zhang, Jongho Kim, Brendan O'Donoghue, Stephen P. Boyd
2021	A*	`conf`	Variational Bayesian Optimistic Sampling. NeurIPS Brendan O'Donoghue, Tor Lattimore
2021	J	`jnl`	Variational Bayesian Optimistic Sampling. CoRR Brendan O'Donoghue, Tor Lattimore
2021	A*	`conf`	Variational Bayesian Reinforcement Learning with Regret Bounds. NeurIPS Brendan O'Donoghue
2020	J	`jnl`	Globally Convergent Type-I Anderson Acceleration for Nonsmooth Fixed-Point Iterations. SIAM J. Optim. Junzi Zhang, Brendan O'Donoghue, Stephen P. Boyd
2020	A*	`conf`	Making Sense of Reinforcement Learning and Probabilistic Inference. ICLR Brendan O'Donoghue, Ian Osband, Catalin Ionescu
2020	J	`jnl`	Making Sense of Reinforcement Learning and Probabilistic Inference. CoRR Brendan O'Donoghue, Ian Osband, Catalin Ionescu
2020	J	`jnl`	Sample Efficient Reinforcement Learning with REINFORCE. CoRR Junzi Zhang, Jongho Kim, Brendan O'Donoghue, Stephen P. Boyd
2020	J	`jnl`	Solving Mixed Integer Programs Using Neural Networks. CoRR Vinod Nair, Sergey Bartunov, Felix Gimeno, Ingrid von Glehn, Pawel Lichocki, Ivan Lobov, Brendan O'Donoghue, Nicolas Sonnerat, Christian Tjandraatmadja, Pengming Wang, Ravichandra Addanki, Tharindi Hapuarachchi, Thomas Keck, James Keeling, Pushmeet Kohli, Ira Ktena, Yujia Li, Oriol Vinyals, Yori Zwols
2020	J	`jnl`	Stochastic matrix games with bandit feedback. CoRR Brendan O'Donoghue, Tor Lattimore, Ian Osband
2019	A*	`conf`	Hamiltonian descent for composite objectives. NeurIPS Brendan O'Donoghue, Chris J. Maddison
2019	—	`conf`	Verification of Non-Linear Specifications for Neural Networks. ICLR (Poster) Chongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
2019	J	`jnl`	Verification of Non-Linear Specifications for Neural Networks. CoRR Chongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
2018	A*	`conf`	Adversarial Risk and the Dangers of Evaluating Against Weak Attacks. ICML Jonathan Uesato, Brendan O'Donoghue, Pushmeet Kohli, Aäron van den Oord
2018	J	`jnl`	Adversarial Risk and the Dangers of Evaluating Against Weak Attacks. CoRR Jonathan Uesato, Brendan O'Donoghue, Aäron van den Oord, Pushmeet Kohli
2018	J	`jnl`	Hamiltonian Descent Methods. CoRR Chris J. Maddison, Daniel Paulin, Yee Whye Teh, Brendan O'Donoghue, Arnaud Doucet
2018	J	`jnl`	Strength in Numbers: Trading-off Robustness and Computation via Adversarially-Trained Ensembles. CoRR Edward Grefenstette, Robert Stanforth, Brendan O'Donoghue, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli
2018	A*	`conf`	The Uncertainty Bellman Equation and Exploration. ICML Brendan O'Donoghue, Ian Osband, Rémi Munos, Volodymyr Mnih
2018	J	`jnl`	Training verified learners with learned verifiers. CoRR Krishnamurthy Dvijotham, Sven Gowal, Robert Stanforth, Relja Arandjelovic, Brendan O'Donoghue, Jonathan Uesato, Pushmeet Kohli
2018	J	`jnl`	Variational Bayesian Reinforcement Learning with Regret Bounds. CoRR Brendan O'Donoghue
2017	—	`conf`	Combining policy gradient and Q-learning. ICLR (Poster) Brendan O'Donoghue, Rémi Munos, Koray Kavukcuoglu, Volodymyr Mnih
2017	J	`jnl`	The Uncertainty Bellman Equation and Exploration. CoRR Brendan O'Donoghue, Ian Osband, Rémi Munos, Volodymyr Mnih
2016	J	`jnl`	Conic Optimization via Operator Splitting and Homogeneous Self-Dual Embedding. J. Optim. Theory Appl. Brendan O'Donoghue, Eric Chu, Neal Parikh, Stephen P. Boyd
2016	J	`jnl`	PGQ: Combining policy gradient and Q-learning. CoRR Brendan O'Donoghue, Rémi Munos, Koray Kavukcuoglu, Volodymyr Mnih
2015	J	`jnl`	Adaptive Restart for Accelerated Gradient Schemes. Found. Comput. Math. Brendan O'Donoghue, Emmanuel J. Candès
2015	J	`jnl`	Large-Scale Convex Optimization for Dense Wireless Cooperative Networks. CoRR Yuanming Shi, Jun Zhang, Brendan O'Donoghue, Khaled Ben Letaief
2015	J	`jnl`	Large-Scale Convex Optimization for Dense Wireless Cooperative Networks. IEEE Trans. Signal Process. Yuanming Shi, Jun Zhang, Brendan O'Donoghue, Khaled Ben Letaief
2014	J	`jnl`	Fast Alternating Direction Optimization Methods. SIAM J. Imaging Sci. Tom Goldstein, Brendan O'Donoghue, Simon Setzer, Richard G. Baraniuk
2014	J	`jnl`	Performance Bounds and Suboptimal Policies for Multi-Period Investment. Found. Trends Optim. Stephen P. Boyd, Mark T. Müller, Brendan O'Donoghue, Yang Wang
2013	J	`jnl`	A Splitting Method for Optimal Control. IEEE Trans. Control. Syst. Technol. Brendan O'Donoghue, Giorgos Stathopoulos, Stephen P. Boyd
2013	—	`conf`	Iterated approximate value functions. ECC Brendan O'Donoghue, Yang Wang, Stephen P. Boyd
2011	—	`conf`	Min-max approximate dynamic programming. CACSD Brendan O'Donoghue, Yang Wang, Stephen P. Boyd